Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    locker

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plants
    -0.07
    piration
    -0.07
    िश
    -0.07
    可是
    -0.06
     Drama
    -0.06
    _python
    -0.06
     Moon
    -0.06
     quarterback
    -0.06
    Item
    -0.06
     serpent
    -0.06
    POSITIVE LOGITS
     hjem
    0.07
     Triple
    0.06
    حاد
    0.06
    .Cor
    0.06
     böl
    0.06
    дом
    0.06
    рай
    0.06
     هیچ
    0.06
    locker
    0.06
     calam
    0.06
    Act Density 0.003%

    No Known Activations